An incremental neural network with a reduced architecture
Neural Networks
Hi-index | 0.00 |
Although traditional techniques of machine learning have, in many cases, presented good results, they have been inefficient for data which are constantly expanding and changing over time. To address these problems, new learning techniques have been proposed in the literature. In this paper we propose a technique called ePNN presenting aspects of this recent paradigm of learning. We carried out a series of experiments that showed its efficiency over previous approaches.